hermes-blind

SkillGitHubActivePython

Recovers the original goal of a long Claude Code or Codex session from its first user turn, so you can restate it before continuing — plus a prompt wrapper that adds evidence and hedging constraints to evaluation prompts. Deterministic, local, no model calls. Experimental.

Description provenance: Original source

Open canonical source

Measured: Oct 16, 2026 · 21 observations

Domains & Uses

Domains: Agents, skills and MCP
Uses: Agent skills, Observability, Code assistants

Installation

/plugin marketplace add hermes-labs-ai/hermes-blind

Check at the source

Compatibility and prerequisites must be checked in the official documentation.

https://github.com/hermes-labs-ai/hermes-blind

Classifications

Nature: Tool

Measurement history

Comparable readings are grouped by signal and unit.

Stars

10stars · Oct 16, 2026

0 (0 %)since Oct 10, 2026

Exact values · 7 readings

Measured	stars	Change
Oct 16, 2026	10	0
Oct 15, 2026	10	0
Oct 14, 2026	10	0
Oct 13, 2026	10	0
Oct 12, 2026	10	0
Oct 11, 2026	10	0
Oct 10, 2026	10	·